Pith. sign in

REVIEW 3 cited by

Survey on Generalization Theory for Graph Neural Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.15650 v1 pith:P6GYH5X3 submitted 2025-03-19 cs.LG cs.AIstat.ML

Antonis Vasileiou , Stefanie Jegelka , Ron Levie , Christopher Morris This is my paper · ORCID
classification cs.LGcs.AIstat.ML
keywords generalizationmpnnsabilitiesattentiongraphgraphsnetworksneural
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Message-passing graph neural networks (MPNNs) have emerged as the leading approach for machine learning on graphs, attracting significant attention in recent years. While a large set of works explored the expressivity of MPNNs, i.e., their ability to separate graphs and approximate functions over them, comparatively less attention has been directed toward investigating their generalization abilities, i.e., making meaningful predictions beyond the training data. Here, we systematically review the existing literature on the generalization abilities of MPNNs. We analyze the strengths and limitations of various studies in these domains, providing insights into their methodologies and findings. Furthermore, we identify potential avenues for future research, aiming to deepen our understanding of the generalization abilities of MPNNs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation

    cs.LG 2026-02 conditional novelty 6.0 of 10

    Message-passing GNNs are shown to be Hölder-continuous and separation-powerful on a new compact space of 'bofop-signals' that includes sparse and dense graphs of all sizes, giving universal approximation and generaliz...

  2. On the Rademacher Complexity of Graph Neural Networks: Unifying Expressivity and Geometry

    cs.LG 2025-10 conditional novelty 5.0 of 10

    For any GNN whose outputs are constant on coloring-induced equivalence classes, empirical Rademacher complexity is at most sqrt(p/m), where p is the number of color classes in the sample.

  3. From Features to Structure: Task-Aware Graph Construction for Relational and Tabular Learning with GNNs

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Selective task-aware attribute promotion into graph nodes improves GNN classification on relational and tabular data compared to schema-based and heuristic graph construction.

Pith tools